CN116775180A

CN116775180A - Record generation method, electronic device, storage medium, and program product

Info

Publication number: CN116775180A
Application number: CN202310574777.8A
Authority: CN
Inventors: 黄晨升; 张晨露; 柴金祥
Original assignee: Shanghai Movu Technology Co Ltd; Mofa Shanghai Information Technology Co Ltd
Current assignee: Shanghai Movu Technology Co Ltd; Mofa Shanghai Information Technology Co Ltd
Priority date: 2023-05-20
Filing date: 2023-05-20
Publication date: 2023-09-19

Abstract

The application provides a record generation method, an electronic device, a computer readable storage medium and a computer program product, which are used for providing record generation function for virtual object interaction process, wherein the method comprises the following steps: receiving an access request from first terminal equipment, and establishing communication connection between the first terminal equipment and a target server; receiving one or more input information of a user through the first terminal equipment in the interaction process of the user and the virtual object; acquiring semantic information of the user according to all input information; and generating a first electronic record according to the semantic information and a preset record template, wherein the display mode in the first electronic record comprises one or more forms of texts, tables and graphs. According to the application, the electronic record is automatically generated according to the semantic information of the user and the preset record template, so that the efficiency is high, errors are not easy to occur, the workload of lawyers, consultants and other service personnel is reduced, and the working efficiency and the service quality are improved.

Description

Record generation method, electronic device, storage medium, and program product

Technical Field

The present application relates to the field of virtual man and artificial intelligence, and more particularly, to a record generation method, an electronic device, a computer-readable storage medium, and a computer program product.

Background

The virtual objects include virtual humans, virtual animals, virtual cartoon figures, and the like. The virtual person is a personified image constructed by CG technology and operated in a code form, and has various interaction modes such as language communication, expression, action display and the like. The technology of the dummy person has been rapidly developed in the field of artificial intelligence and has been applied in many technical fields such as video, media, games, finance, travel, education, medical and so on. The interactive function of the virtual object can enhance the immersion and experience of the user and improve the satisfaction and loyalty of the user. The user may establish a communication connection with the server through a terminal device (e.g., a smart phone, a tablet computer, etc.) and interact with the virtual object. During the interaction, the user may provide text information, voice information, or image information.

Currently, in order to facilitate a user or a service party such as an enterprise, a platform, etc. to view and analyze the interaction process between the user and the virtual object, a detailed record needs to be generated. To achieve this, the conventional method typically records the input information of the user in text form, and then manually collates and analyzes the input information to finally generate a record. However, this approach is inefficient and error prone.

Based on this, the present application provides a record generating method, an electronic device, a computer readable storage medium and a computer program product to improve the prior art.

Disclosure of Invention

The application aims to provide a record generation method, electronic equipment, a computer readable storage medium and a computer program product, which can automatically generate an electronic record according to semantic information of a user and a preset record template, and have high efficiency and are not easy to make mistakes.

The application adopts the following technical scheme:

in a first aspect, the present application provides a record generating method for providing a record generating function for a virtual object interaction process, the method comprising:

receiving an access request from first terminal equipment, and establishing communication connection between the first terminal equipment and a target server, wherein the target server is used for providing a virtual object interaction function;

receiving one or more input information of a user through the first terminal equipment in the interaction process of the user and the virtual object, wherein each input information is text information, voice information or image information;

acquiring semantic information of the user according to all input information;

And generating a first electronic record according to the semantic information and a preset record template, wherein the display mode in the first electronic record comprises one or more forms of texts, tables and graphs.

The beneficial effect of this technical scheme lies in: the method has the advantages that a record generating function is provided for the virtual object interaction process, and useful information in the user interaction process is effectively obtained through semantic extraction, so that the record is more accurate and comprehensive; according to the semantic information of the user and the preset recording template, the electronic record is automatically generated, the efficiency is high, errors are not easy to occur, the workload of service personnel such as lawyers, consultants and the like is reduced, the time and the energy are saved, the working efficiency and the service quality are improved, and the labor cost is reduced; through semantic analysis of the user interaction information, service personnel such as lawyers and consultants are helped to better know the user demands and the concerns, more accurate and professional services are provided for the lawyers and the consultants, customer satisfaction and loyalty are improved, and accurate sales is realized; electronic records are displayed in various forms such as texts, tables and graphics, so that the readability and the visual effect of the records are enhanced, and the understanding and acceptance degree of readers are improved.

In some alternative implementations, the process of obtaining the record template includes:

Receiving configuration operation of a configuration personnel through a second terminal device to obtain recording configuration information, wherein the recording configuration information is used for configuring one or more of a control, a font, a word size, a color, a text length, a file format and typesetting;

and configuring the record template according to the record configuration information.

The beneficial effect of this technical scheme lies in: the configuration personnel is allowed to carry out custom configuration on the record template, so that the generated record can better meet the requirements and aesthetic requirements of different clients, and the practicality and readability of the record are improved; the recording template can be adjusted according to the operation of configuration personnel, so that the recording template can be rapidly adapted to change in different scenes or industries, and the universality and expandability of the recording generation method are improved; personalized record template configuration can be provided for different clients according to the characteristics and the requirements of the different clients, so that the accuracy and satisfaction of record generation are further improved, and accurate sales can be realized; the method is easy to operate and flexible in recording template configuration mode, and is beneficial to further reducing the workload of professionals such as lawyers, consultants and the like and improving the working efficiency. In summary, by introducing the record template configuration function, the technical scheme enables the record generation process to be more flexible and personalized, thereby improving the practicality, pertinence and readability of the record. Meanwhile, accurate sales can be realized, and the working efficiency of professionals such as lawyers, consultants and the like can be improved.

In some alternative implementations, the method further includes:

and generating a second electronic record according to the semantic information and a preset recording rule, wherein the display mode in the second electronic record comprises one or more forms of texts, tables, graphics, voice, animation and images.

The beneficial effect of this technical scheme lies in: the method and the device have the advantages that the readability, intuitiveness, customization and propagation effect of the record are improved, the expandability of the record is improved, and the requirements of different users and scenes are met. Specifically, the second electronic record is presented in a plurality of display modes, so that reading habits and requirements of different users can be met, and the legibility and user experience of the record are improved; the multiple display modes are helpful for more intuitively presenting data and information, facilitating the rapid capture of key information by a user and improving the understanding degree of the user on the recorded content; by generating the second electronic record, customized information can be provided for different personnel (such as service personnel, managers, users and the like), so that the requirements of different roles are met, and the use value of the information is improved; the records are attractive and shareable by various display forms, so that the influence range and the transmission effect of the records are enlarged; the method is beneficial to improving the expandability of the record, and can conveniently adjust the record content and structure according to different scenes and requirements through preset record rules and various display forms, thereby realizing flexible customization of the record.

In some alternative implementations, when the input information of the user includes voice information, in the second electronic record, the presentation includes voice, and the presentation includes all voice information input by the user;

when the input information of the user comprises image information, in the second electronic record, the display mode comprises images, and the display content comprises all the image information input by the user.

The beneficial effect of this technical scheme lies in: by displaying all voice and image information input by a user in the second electronic record, the enrichment and diversification of recorded content are realized, the recorded information integrity, accuracy, readability and user experience are improved, multi-mode information processing is supported, and the information transfer effect is improved. Specifically, by displaying all voice and image information input by a user in the second electronic record, original information can be reserved, and the integrity and accuracy of the recorded information are improved; by adding voice and image information input by a user into the record, the content and the form of the record can be enriched, and the readability and the attraction of the record are enhanced; the display form of the record is automatically adjusted according to the input information type of the user, so that the requirements and reading habits of the user can be better met, and the user experience is improved; by displaying voice and image information in the record, multi-mode information processing can be supported, and the efficiency and accuracy of information processing can be improved; by displaying the voice and image information in the record, the information can be presented more intuitively, the effect of information transfer is improved, and the user can conveniently and rapidly capture key information.

In some alternative implementations, the method further includes:

and sending the first electronic record and/or the second electronic record to a third terminal device of a target service person so that the target service person provides services for the user according to the first electronic record and/or the second electronic record.

The beneficial effect of this technical scheme lies in: by sending the electronic records to the third terminal equipment of the target service personnel, the real-time performance and convenience of record transmission are realized, and the target service personnel can acquire the records in time, so that the user requirements can be responded more quickly, and the service quality and efficiency are improved; the target service personnel provide services for the users according to the electronic records, so that the pertinence and the accuracy of the services are enhanced, and the target service personnel can better know the requirements, the problems and the concerns of the users according to the information in the records, thereby providing more accurate and professional services; the communication efficiency between the target service personnel and the user is improved, the target service personnel can better know the problem of the user through the information in the record, unnecessary communication cost is avoided, and the communication efficiency is improved; by providing detailed electronic records for the target service personnel, the target service personnel can provide professional and accurate services according to the specific requirements of users, so that the user satisfaction is improved, and the user loyalty is enhanced; the system is beneficial to collecting and analyzing the working data of the target service personnel, and by tracking and analyzing the use condition recorded on the third terminal equipment, a manager can know the data of the target service personnel in the aspects of working efficiency, service quality and the like, so that a more reasonable management strategy and training plan are formulated.

In some alternative implementations, the process of obtaining the target attendant includes:

acquiring the first N labels of the semantic information, wherein N is a positive integer;

respectively acquiring the first N labels of a plurality of service personnel;

respectively calculating the similarity of the label of the semantic information and the label of each service person;

and taking the service personnel corresponding to the highest similarity as the target service personnel.

The beneficial effect of this technical scheme lies in: by calculating the similarity between the semantic information label and the service personnel label, the accurate matching and dynamic distribution of the target service personnel are realized, and the service quality, the user satisfaction and the work efficiency of the target service personnel are improved. Specifically, by calculating the similarity between the semantic information label and the service personnel label, the professional ability of the target service personnel and the user demand can be more accurately matched, so that the service quality and the user satisfaction degree are improved; the dynamic allocation of the target service personnel is facilitated, the allocation of the target service personnel can be automatically adjusted according to the change of the user demand and the real-time state of the target service personnel, and the resource utilization rate and the service efficiency are improved; by matching the target service personnel with the highest similarity, unnecessary communication and coordination cost can be reduced, and the working efficiency of the target service personnel can be improved; the method is beneficial to collecting and analyzing the professional ability data of the target service personnel, and through statistics and analysis of the labels of the target service personnel, a manager can know the professional ability distribution of the target service personnel, so that more reasonable personnel training and development plans are formulated.

In some optional implementations, the acquiring the first N tags of the semantic information includes:

detecting whether the user is a return guest;

when the user is a back-end guest, in the interaction process, the first terminal equipment is used for playing a first interaction video, and in the first interaction video, the virtual object inquires whether the user is satisfied with a history service personnel serving the user last time;

receiving feedback information of the user by using the first terminal equipment;

detecting whether the user is satisfied with the history service personnel according to the feedback information;

when the user is satisfied with the history service personnel, taking the history service personnel as the target service personnel;

and when the user is not satisfied with the history service personnel, acquiring the first N labels of the semantic information.

The beneficial effect of this technical scheme lies in: the service distribution is more personalized and accurate, the service quality, the user satisfaction and the service efficiency are improved, and a long-term user relationship is established. Specifically, whether the user is a return customer or not is detected, so that loyalty and historical service conditions of the user can be identified, and more personalized and accurate service is provided for the user; feedback of the user on the service quality can be collected in time by inquiring the satisfaction degree of the user on the historical service personnel, and a basis is provided for improving the service quality and the satisfaction degree of the user; when users satisfy the historical service personnel, the historical service personnel are directly used as target service personnel, so that the service distribution time and resource consumption are reduced, and the service efficiency is improved; when the user is not satisfied with the history service personnel, the first N labels of the semantic information are acquired according to the feedback information of the user, so that the user requirements and the professional ability of the target service personnel are better matched, and the service quality is improved; the method is beneficial to establishing long-term user relationship, and the satisfaction degree and the loyalty degree of users can be improved by paying attention to and adjusting the satisfaction degree of the returning customers, so that the customer population is further expanded.

In some alternative implementations, the method further includes:

in the interaction process, identifying emotion categories of the users according to the received input information;

detecting whether the emotion classification belongs to a preset emotion classification set, wherein the preset emotion classification set comprises one or more of impatience, boring, collapse, pain, anxiety, sadness, anger, fear and depression;

and when the emotion category belongs to the preset emotion category set, playing a second interactive video by using the first terminal device, wherein in the second interactive video, the virtual object pacifies the emotion of the user.

The beneficial effect of this technical scheme lies in: by acquiring the emotion category of the user and taking corresponding measures according to the emotion category, timely response and processing of the emotion of the user are realized, user experience, interactivity, emotion stability and service efficiency are improved, and meanwhile, the service process is optimized. Specifically, by detecting the emotion type of the user and playing the second interactive video, the emotion of the user is pacified by adopting the virtual object, the demand and emotion change of the user can be responded in time, the interactivity with the user is enhanced, and the user is more concerned and concerned; the negative emotion of the user is pacified in time, so that the stability of the emotion of the user is recovered, and the sensitivity of the user to problems in the service process is reduced; by timely responding and processing the emotion of the user, the service process can be optimized, and the pertinence and individuation of the service are improved.

In a second aspect, the present application provides an electronic device for providing record generation functionality for a virtual object interaction process, the electronic device comprising a memory and at least one processor, the memory storing a computer program, the at least one processor being configured to implement the following steps when executing the computer program:

and generating a first electronic record according to all input information of the user and a preset record template, wherein in the first electronic record, the display mode comprises one or more forms of texts, tables and graphs.

In a third aspect, the present application provides a computer-readable storage medium storing a computer program which, when executed by at least one processor, performs the steps of any of the methods or performs the functions of any of the electronic devices described above.

In a fourth aspect, the application provides a computer program product comprising a computer program which, when executed by at least one processor, performs the steps of any of the methods or performs the functions of any of the electronic devices described above.

Drawings

The application is further described below with reference to the drawings and the detailed description.

Fig. 1 is a flow chart of a record generating method according to an embodiment of the present application.

Fig. 2 is a schematic flow chart of a method for acquiring a target service person according to an embodiment of the present application.

Fig. 3 is a block diagram of an electronic device according to an embodiment of the present application.

Fig. 4 is a schematic structural diagram of a computer program product according to an embodiment of the present application.

Detailed Description

The technical scheme of the present application will be described below with reference to the drawings and the specific embodiments of the present application, and it should be noted that, on the premise of no conflict, new embodiments may be formed by any combination of the embodiments or technical features described below.

In embodiments of the application, words such as "exemplary" or "such as" are used to mean serving as an example, instance, or illustration. Any implementation or design described as "exemplary" or "e.g." in the examples of this application should not be construed as preferred or advantageous over other implementations or designs. Rather, the use of words such as "exemplary" or "such as" is intended to present related concepts in a concrete fashion.

The first, second, etc. descriptions in the embodiments of the present application are only used for illustration and distinction of description objects, and no order division is used, nor does it represent a particular limitation on the number in the embodiments of the present application, nor should it constitute any limitation on the embodiments of the present application.

The technical fields and related terms of the embodiments of the present application are briefly described as follows.

The virtual objects include virtual humans, virtual animals, virtual cartoon figures, and the like. The virtual person is a personified image constructed by CG technology and operated in a code form, and has various interaction modes such as language communication, expression, action display and the like. The technology of virtual persons has been rapidly developed in the field of artificial intelligence and has been applied in many technical fields such as video, media, games, finance, travel, education, medical treatment, etc., and not only can a virtual host, a virtual anchor, a virtual training lecturer, a virtual customer service, a virtual lawyer, a virtual teacher, a virtual idol, a virtual doctor, a virtual lecturer, a virtual assistant, etc., but also a video can be generated through text or audio one-key. In the virtual people, the service type virtual people mainly have the functions of replacing real people to serve and provide daily accompaniment, are the virtualization of service type roles in reality, and have the industrial value of mainly reducing the cost of the existing service type industry and enhancing the cost reduction of the stock market.

Artificial intelligence (Artificial Intelligence, AI) is the theory, method, technique and application system that uses a digital computer or a machine controlled by a digital computer to simulate, extend and extend human intelligence, sense the environment, acquire knowledge and use the knowledge to obtain optimal results. In other words, artificial intelligence is an integrated technology of computer science that attempts to understand the essence of intelligence and to produce a new intelligent machine that can react in a similar way to human intelligence. The design principle and the implementation method of various intelligent machines are researched by artificial intelligence, so that the machines have the functions of perception, reasoning and decision. The artificial intelligence technology is a comprehensive subject, and relates to the technology with wide fields, namely the technology with a hardware level and the technology with a software level. Artificial intelligence infrastructure technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technologies, operation/interaction systems, mechatronics, and the like. The artificial intelligence software technology mainly comprises a computer vision technology, a voice processing technology, a natural language processing technology, machine learning/deep learning, automatic driving, intelligent traffic and other directions.

Machine Learning (ML) is a multi-domain interdisciplinary, involving multiple disciplines such as probability theory, statistics, approximation theory, convex analysis, algorithm complexity theory, etc. The computer program may learn experience E given a certain class of tasks T and performance metrics P, and increase with experience E if its performance in task T happens to be measured by P. Machine learning is specialized in studying how a computer simulates or implements learning behavior of a human to acquire new knowledge or skills, reorganizing existing knowledge structures to continually improve its own performance. Machine learning is the core of artificial intelligence, a fundamental approach to letting computers have intelligence, which is applied throughout various areas of artificial intelligence.

Deep learning is a special machine learning by which the world is represented using a hierarchy of nested concepts, each defined as being associated with a simple concept, and achieving great functionality and flexibility, while a more abstract representation is computed in a less abstract way. Machine learning and deep learning typically include techniques such as artificial neural networks, belief networks, reinforcement learning, transfer learning, induction learning, teaching learning, and the like.

The virtual object interaction application is used for providing virtual object interaction functions. Virtual objects can simulate human communication and behavior and interact with users. Such software (referred to as virtual human interactive applications) is typically driven by artificial intelligence and natural language processing techniques and is capable of interacting with a user by means of text, speech, images, forms, etc.

The interactive function of the virtual object can enhance the immersion and experience of the user and improve the satisfaction and loyalty of the user. The user may establish a communication connection with the server through a terminal device (e.g., a smart phone, a tablet computer, etc.) and interact with the virtual object. During the interaction, the user may provide text information, voice information, or image information.

The scheme provided by the embodiment of the application relates to technologies such as virtual man, interactive design, artificial intelligence, 3D modeling, cloud computing and the like, and is specifically described by the following embodiment. The following description of the embodiments is not intended to limit the preferred embodiments.

(record generating method)

Referring to fig. 1, fig. 1 is a flowchart of a record generating method according to an embodiment of the present application.

The embodiment of the application provides a record generation method for providing a record generation function for a virtual object interaction process, which comprises the following steps:

step S101: receiving an access request from first terminal equipment, and establishing communication connection between the first terminal equipment and a target server, wherein the target server is used for providing a virtual object interaction function;

step S102: receiving one or more input information of a user through the first terminal equipment in the interaction process of the user and the virtual object, wherein each input information is text information, voice information or image information;

step S103: acquiring semantic information of the user according to all input information;

step S104: and generating a first electronic record according to the semantic information and a preset record template, wherein the display mode in the first electronic record comprises one or more forms of texts, tables and graphs.

The record generation method can be operated on the electronic equipment, the electronic equipment and the first terminal equipment (used by a user) can be independent, and the electronic equipment and the first terminal equipment can be integrated. When the electronic device and the first terminal device are independent, the electronic device may be a computer, a server (including a cloud server), or the like having computing power.

The terminal device (including the first terminal device, the second terminal device, the third terminal device, etc.) is not limited in the embodiment of the present application, and may be, for example, an intelligent terminal device having a display screen, a microphone, and a speaker, such as a mobile phone, a tablet computer, a notebook computer, a desktop computer, and an intelligent wearable device, or may also be a workstation or a console having a display screen, a microphone, and a speaker. The display screen may be a touch display screen or a non-touch display screen.

In an embodiment of the present application, the virtual object includes one or more of a virtual person, a virtual animal, and a virtual cartoon character. As one example, the virtual object is a virtual person "JING" (chinese name: mirror).

The interactive video of the virtual object may provide the user with a lot of useful information and suggestions or guide the user. For example, the user can learn various service information of an enterprise in an interactive video of an enterprise service virtual man, learn knowledge and answering skills of textbooks in an interactive video of a virtual teacher, learn medical knowledge such as disease symptoms in an interactive video of a virtual doctor, or learn historical background, cultural significance, artistic value and the like of a museum collection of cultural relics in an interactive video of a virtual museum lecturer.

Herein, the configurator and the service staff are generally staff members of the clients, the working contents of the configurator include configuring the recording templates and the recording rules, and the working contents of the service staff include providing services for the users. The configurator and service personnel may be overlapping, i.e. one staff member a of the customer may be both configurator and service personnel. The client refers to a client of a virtual object interactive application, typically a B-end client of an enterprise, a organization, a bank, a school, a hospital, etc., and also a small number of C-end clients. A user in this context generally refers to a user of the above-mentioned customer, not a configurator or service person.

The target server may run one or more applications for providing virtual object interaction functionality. These applications may be written using one or more programming languages, such as Java, python, node. Js, etc., and may utilize various frameworks and libraries to implement various functions, such as natural language processing, speech-to-text, image recognition, etc. To improve availability and performance of the target server, a load balancer may be used to distribute requests across multiple servers, and a failover mechanism may be used to automatically switch to a standby server in the event of a failure of the target server. The electronic device and the target server can be independent, and the electronic device and the target server can be integrated.

The interactive video of the virtual object is stored on one or more servers, which may store the video using cloud storage or owned storage, or the like. To collect user information, form buttons may be provided in the virtual object interactive application and the form may be designed in the background configuration interface. Form data generated by filling in the form by a user is stored in a database or other data storage system, the data can be stored by using a MySQL, mongoDB relational or non-relational database, and the data storage and management can be realized by using cloud storage or other technologies.

Therefore, a record generating function is provided for the virtual object interaction process, and useful information in the user interaction process is effectively obtained through semantic extraction, so that the record is more accurate and comprehensive; automatically generating electronic records according to semantic information of a user and a preset record template, reducing the workload of service personnel such as lawyers, consultants and the like, saving time and energy, improving the working efficiency and the service quality and reducing the labor cost; through semantic analysis of the user interaction information, service personnel such as lawyers and consultants are helped to better know the user demands and the concerns, more accurate and professional services are provided for the lawyers and the consultants, customer satisfaction and loyalty are improved, and accurate sales is realized; electronic records are displayed in various forms such as texts, tables and graphics, so that the readability and the visual effect of the records are enhanced, and the understanding and acceptance degree of readers are improved.

The preset recording template is a recording format preset according to the content and the display mode of the required recording, so that a first electronic recording meeting the requirements can be conveniently generated, and interaction information of the user and the virtual object is displayed in the first electronic recording. The recording template should include necessary information such as user basic information, consultation questions, answer contents, consultation time, etc., so that the service person can accurately know the user's needs and conditions.

In one example, a user sends an access request to a target server of the legal consultation platform through a smart phone (first terminal device), and after the target server receives the access request, a communication connection with the smart phone is established. During the interaction of the user with the virtual lawyer, the user inputs text information (e.g. "i want to consult with the divorce procedure"), voice information (e.g. "i want to consult with the divorce procedure") or image information (e.g. "i upload a photograph of the divorce protocol) through the smartphone. After receiving the input information, the target server extracts the semantics from the input information to obtain the semantic information of the user (for example, the user wants to consult the divorce procedure). Then, the target server generates a first electronic record according to the semantic information and a preset record template. For example, the title of the first electronic record is "divorce consultation record", and the fields of the first electronic record include: customer name, contact, consultation time, question descriptions, virtual lawyer answers, related legal terms, etc. The divorce questions posed by the user are filled in the question description field, the answers of the virtual lawyers are filled in the virtual lawyer answers field, the relevant legal terms are filled in the relevant legal terms field and the like.

In some embodiments, the acquiring semantic information of the user according to all input information (i.e. step S103) includes: extracting semantics from the input information by using a semantic extraction model corresponding to the input information aiming at each piece of the input information so as to obtain the semantics of the input information; and acquiring semantic information of the user according to the semantics of all the input information.

Since the semantic extraction is performed for each input information, that is, the semantic extraction may be performed in real time during the interaction, or the semantic extraction may be performed after the interaction is completed.

In some embodiments, when the input information is text information, the semantic extraction model corresponding to the input information is a pre-trained language model based on deep learning; when the input information is voice information, the semantic extraction model corresponding to the input information comprises a voice-to-text model based on deep learning and a pre-training language model based on deep learning; when the input information is image information, the semantic extraction model corresponding to the input information is a semantic segmentation model based on deep learning.

The embodiment of the application uses a model based on deep learning to extract semantic features of input information. For different types of input information, different deep learning models are adopted for semantic extraction, including a pre-training language model, a voice-to-text model, a semantic segmentation model and the like.

For text information, pre-trained language models, such as BERT, GPT, etc., are employed to extract semantic features of the input text. By pre-training a large amount of texts, the models can learn the structure and the semantics of the language, so that the semantics of the input texts can be effectively extracted.

For voice information, a voice-to-text model based on deep learning, such as CTC, transformer, is adopted to convert the voice information into text information, and a pre-training language model is adopted to extract semantic features of the text information. Thus, semantics related to the input information can be extracted from the voice information.

For image information, a semantic segmentation model based on deep learning, such as UNet, deep Lab and the like, is adopted to segment the image, and the semantics corresponding to each pixel point are extracted. Thus, the semantics related to the input information can be extracted from the image accurately.

The method has the advantages that semantic features of input information can be extracted more accurately by using a semantic extraction model based on deep learning, so that accuracy and efficiency of semantic understanding are improved; the pre-training language model can improve the natural language processing capacity, including text classification, emotion analysis, machine translation and other aspects; by adopting different deep learning models, the multi-mode information can be processed, including text information, voice information, image information and the like, so that more comprehensive information processing is realized.

In some embodiments, the process of obtaining the record template includes:

Therefore, configuration personnel are allowed to carry out custom configuration on the record template, so that the generated record can better meet the requirements and aesthetic requirements of different clients, and the practicability and readability of the record are improved; the recording template can be adjusted according to the operation of configuration personnel, so that the recording template can be rapidly adapted to change in different scenes or industries, and the universality and expandability of the recording generation method are improved; personalized record template configuration can be provided for different clients according to the characteristics and the requirements of the different clients, so that the accuracy and satisfaction of record generation are further improved, and accurate sales can be realized; the method is easy to operate and flexible in recording template configuration mode, and is beneficial to further reducing the workload of professionals such as lawyers, consultants and the like and improving the working efficiency. In summary, by introducing the record template configuration function, the technical scheme enables the record generation process to be more flexible and personalized, thereby improving the practicality, pertinence and readability of the record. Meanwhile, accurate sales can be realized, and the working efficiency of professionals such as lawyers, consultants and the like can be improved.

For example, a configurator of a medical consultation company uses a computer (second terminal device) to perform a configuration operation of the record template. The configurator can perform configuration operations through a graphical user interface, such as dragging controls, setting fonts and colors, etc., to obtain the record configuration information.

Control: the configurator can select controls such as graphics, tables or text boxes to display data and information in the records;

font: the configurator may select fonts used in the record, such as Song's font, microsoft's Jack, or Times New Roman, etc.;

word size: the configurator can set different font sizes for the title, the text, the annotation and other parts in the record, such as a font number 16 for the title and a font number 12 for the text;

color: the configurator can set colors for text, charts and backgrounds in the records, such as black for text, red for highlighting key data;

text length: the configurator can limit the text length of certain parts in the record, such as the abstract part to be limited to be within 200 characters;

file format: the configurator can select a file format of record output, such as PDF, word or HTML;

typesetting: the configurator can set typesetting elements such as page layout, margin, line spacing and the like of the records.

And automatically generating a recording template according to the recording configuration information. The recording template comprises the following parts:

title: topics of records, such as "medical consultation records";

patient information: fields including basic information, medical history, and symptoms of the patient;

consultation process: the interaction process between the patient and the virtual doctor is recorded;

diagnosis results: the diagnosis result given by the virtual doctor is recorded;

advice and treatment regimens: for recording advice and treatment regimens provided by the virtual doctor for the diagnostic results.

Through the recording template acquisition process, a recording template with good typesetting and visual effects is generated according to the configuration operation of the configuration personnel.

In some embodiments, a preview function can be introduced in the configuration process of the record template, and configuration personnel can check the effect of the record template in real time, so that the record generation effect is ensured to meet the expectations, and the accuracy and quality of record generation are improved.

In some embodiments, the method further comprises:

Therefore, the record readability, intuitiveness, customization and propagation effect are improved, the record expandability is improved, and the requirements of different users and scenes are met. Specifically, the second electronic record is presented in a plurality of display modes, so that reading habits and requirements of different users can be met, and the legibility and user experience of the record are improved; the multiple display modes are helpful for more intuitively presenting data and information, facilitating the rapid capture of key information by a user and improving the understanding degree of the user on the recorded content; by generating the second electronic record, customized information can be provided for different personnel (such as service personnel, managers, users and the like), so that the requirements of different roles are met, and the use value of the information is improved; the records are attractive and shareable by various display forms, so that the influence range and the transmission effect of the records are enlarged; the method is beneficial to improving the expandability of the record, and can conveniently adjust the record content and structure according to different scenes and requirements through preset record rules and various display forms, thereby realizing flexible customization of the record.

Wherein the recording rule is a way to automatically generate the second electronic record based on the semantic information. The recording rules can automatically match related sales contents according to the consultation problems and requirements of the users. For example, if the user consults with investment financing, the recording rules may automatically generate fund product recommendation information in the answer content for provision to service personnel as a sales lead. Secondly, the recording rule can self-define and generate the format and the content of the second electronic record according to the sales strategy and the demand of service personnel. For example, specific recording modes and format requirements can be set according to the working needs of service personnel, so that the service personnel can more conveniently view and use the recorded information. In addition, specific record items such as user basic information, contact information, consultation questions, answer contents, consultation time and the like can be set so that service personnel can comprehensively know the condition and the requirement of the user. Finally, the recording rule can automatically record the second electronic record, so that the recording efficiency and accuracy are improved. For example, the recording rules can support various recording modes such as text input, voice recognition, image recognition and the like, and errors and time consumption of manual recording are reduced. Meanwhile, the timeliness and the integrity of the second electronic record can be ensured by the automatic record, so that service personnel can inquire and use the second electronic record at any time.

Taking an online medical consultation platform as an example, a user asks questions to a virtual doctor, for example: "I feel headache, debilitation and sore throat recently. "

And the target server generates a second electronic record according to the preset record rule. Recording rules include matching user symptoms to potential diseases, providing corresponding medical advice, and the like.

The second electronic record displaying mode comprises the following steps:

text: explaining the disease to which the user symptoms may correspond.

Table: listing the correspondence between the symptoms of the user and the underlying disease, as well as treatment advice.

And (3) graphics: the record contains a pie chart or bar chart showing the probability ratios for different disease types, showing the general course of the disease and the expected recovery time using the time axis.

And (3) voice: the patient inputs his own voice.

Animation: the display patient should maintain good lifestyle, take care of rest, etc.

Image: displaying pictures of medicines or medical equipment which need to be used by a patient; and images entered by the patient himself.

The second electronic record is sent to the user, so that the user can be helped to take countermeasures to eliminate symptoms as soon as possible; the second electronic record is sent to the doctor to assist the doctor in diagnosing and treating the patient (i.e., the user).

In some embodiments, when the input information of the user includes voice information, in the second electronic record, the presentation mode includes voice, and the presentation content includes all voice information input by the user;

Therefore, through displaying all voice and image information input by the user in the second electronic record, the enrichment and diversification of recorded content are realized, the recorded information integrity, accuracy, readability and user experience are improved, multi-mode information processing is supported, and the information transfer effect is improved. Specifically, by displaying all voice and image information input by a user in the second electronic record, original information can be reserved, and the integrity and accuracy of the recorded information are improved; by adding voice and image information input by a user into the record, the content and the form of the record can be enriched, and the readability and the attraction of the record are enhanced; the display form of the record is automatically adjusted according to the input information type of the user, so that the requirements and reading habits of the user can be better met, and the user experience is improved; by displaying voice and image information in the record, multi-mode information processing can be supported, and the efficiency and accuracy of information processing can be improved; by displaying the voice and image information in the record, the information can be presented more intuitively, the effect of information transfer is improved, and the user can conveniently and rapidly capture key information.

Taking an online home design consultation platform as an example, a user inputs voice information, for example: "I want to refit my bedroom, want to use modern conciseness, please suggest me. "in the second electronic record, the presentation content includes speech input by the user. The second electronic record may also include a responsive voice in which the virtual object replies to the user in voice form, for example: "according to your demand, we propose your use of light-colored wallpaper, a compact furniture design, and a very simple ornament. In addition, you can also consider adding some plant elements to increase the vigor in the room. "

As another example, the user may enter image information, such as a picture of a bedroom the user may wish to have a fitting suggestion. In the second electronic record, the presentation content includes an image input by the user. The second electronic record may further include the following: analyzing photos provided by a user by using a marking tool, for example, indicating the placement problem of the existing furniture, the color collocation of curtains and the like; a schematic diagram of some designs is provided showing how existing bedroom layouts and decorations can be modified to conform to modern conciseness styles.

In some embodiments, the method further comprises:

Therefore, by sending the electronic record to the third terminal equipment of the target service personnel, the real-time performance and convenience of record transmission are realized, and the target service personnel can acquire the record in time, so that the user demand can be responded more quickly, and the service quality and efficiency are improved; the target service personnel provide services for the users according to the electronic records, so that the pertinence and the accuracy of the services are enhanced, and the target service personnel can better know the requirements, the problems and the concerns of the users according to the information in the records, thereby providing more accurate and professional services; the communication efficiency between the target service personnel and the user is improved, the target service personnel can better know the problem of the user through the information in the record, unnecessary communication cost is avoided, and the communication efficiency is improved; by providing detailed electronic records for the target service personnel, the target service personnel can provide professional and accurate services according to the specific requirements of users, so that the user satisfaction is improved, and the user loyalty is enhanced; the system is beneficial to collecting and analyzing the working data of the target service personnel, and by tracking and analyzing the use condition recorded on the third terminal equipment, a manager can know the data of the target service personnel in the aspects of working efficiency, service quality and the like, so that a more reasonable management strategy and training plan are formulated.

For example, a user sends an access request to a virtual advisor of a real estate company through a smart phone (first terminal device), asking for detailed information about a certain house source.

The virtual advisor interacts with the user and the target server receives input from the user via the smart phone, including text information (e.g., house source location, house type, budget, etc.) and voice information (e.g., specific requirements regarding the house source).

After the interaction is finished, the target server extracts semantic information from all input information of the user, such as 'three rooms and two halls', 'near subway station', 'budget 500 ten thousand', and the like.

And generating a first electronic record by the target server according to the extracted semantic information and a preset record template. The first electronic record shows the requirements and preferences of the user, and the first electronic record is shown in text, forms, graphics and the like, such as:

basic information of the user: name, contact, etc.;

room source requirements: house type, place, budget, etc.;

specific requirements are: such as near subway stations, school rooms, etc.

The target server sends the first electronic record to a tablet (third terminal device) of the real estate agent (target service person). Real estate agents may learn the needs and preferences of users from records to provide more accurate and professional source recommendation services for users.

Referring to fig. 2, fig. 2 is a schematic flow chart of acquiring a target service person according to an embodiment of the present application.

In some embodiments, the process of obtaining the targeted attendant comprises:

respectively acquiring the first N labels of a plurality of service personnel;

It should be noted that, on the premise of being able to be realized, the above steps of acquiring the semantic information tag and the step of acquiring the service personnel tag may be interchanged, which is not limited by the present application.

In some embodiments, the calculating the similarity between the tag of the semantic information and the tag of each service person includes: for each of the service personnel, the following processing is performed: and inputting the label of the semantic information and the label of the service personnel into a similarity model to obtain the similarity between the label of the semantic information and the label of the service personnel. The similarity model may be obtained by training a deep learning-based model, and the deep learning-based model may include a Convolutional Neural Network (CNN), a Recurrent Neural Network (RNN), a long-short-term memory network (LSTM), and the like, for example.

Therefore, by calculating the similarity between the semantic information label and the service personnel label, the accurate matching and dynamic distribution of the target service personnel are realized, and the service quality, the user satisfaction and the work efficiency of the target service personnel are improved. Specifically, by calculating the similarity between the semantic information label and the service personnel label, the professional ability of the target service personnel and the user demand can be more accurately matched, so that the service quality and the user satisfaction degree are improved; the dynamic allocation of the target service personnel is facilitated, the allocation of the target service personnel can be automatically adjusted according to the change of the user demand and the real-time state of the target service personnel, and the resource utilization rate and the service efficiency are improved; by matching the target service personnel with the highest similarity, unnecessary communication and coordination cost can be reduced, and the working efficiency of the target service personnel can be improved; the method is beneficial to collecting and analyzing the professional ability data of the target service personnel, and through statistics and analysis of the labels of the target service personnel, a manager can know the professional ability distribution of the target service personnel, so that more reasonable personnel training and development plans are formulated.

For example, a user interacts with a virtual lawyer assistant at a law firm, the user providing input about legal questions, such as: "I need a lawyer who is good at the work law because I have a contract dispute with the company. "

The target server extracts semantic information from the information provided by the user and generates the first N tags (e.g., n=3), for example: the labor law, the labor contract and the dispute are shown.

The target server stores information of a plurality of lawyers, and queries the first N labels of each lawyer, such as:

lawyer a label: [ "labor law", "labor contract", "contract review" ];

lawyer B label: [ "real estate method", "real estate transaction", "dispute" ];

lawyer C label: [ "criminal law", "criminal dialect", "infringement" ].

The target server calculates the similarity of the semantic information label of the user and the label of each lawyer, for example, the similarity corresponding to lawyer A, B, C is 70%, 30%, 10% respectively, and the lawyer corresponding to the highest similarity is lawyer a.

And the target server takes the lawyer A corresponding to the highest similarity as a recommended target service person.

In some embodiments, the obtaining the first N tags of the semantic information includes:

detecting whether the user is a return guest;

Receiving feedback information of the user by using the first terminal equipment; the feedback information is text information, voice information or image information;

In some embodiments, the process of detecting whether the user is a return guest comprises: extracting a user identification from the access request, such as a user login credential, a device identification code (e.g., IMEI number, MAC address, etc.), an IP address, or other information useful for identifying the user; inquiring a historical record related to the extracted user identification in a database, wherein the historical record comprises interaction with a virtual object before a user, a service request, a processing result and the like; based on the queried history, analyzing whether the user has used the relevant service in the past, for example, it may be checked whether the user has posed a problem to the virtual object or has obtained a service; if the analysis result shows that the user uses the related service, the user can be regarded as a return guest; otherwise, if no relevant record is queried or the user has not used the service in the past, the user is regarded as a new client. Through the steps, whether the user is a return guest can be identified, and the service strategy is adjusted accordingly, so that the user satisfaction degree and the service quality are improved. For example, for return guests, they may be prioritized for familiar service personnel, or personalized recommendations may be provided during the interaction, etc.

In some embodiments, the detecting whether the user is satisfied with the history service person according to the feedback information includes: and inputting the feedback information into a satisfaction model to obtain a satisfaction evaluation result, wherein the satisfaction evaluation result is used for indicating satisfaction or dissatisfaction. The satisfaction model may be obtained by training a deep learning-based model, for example, and the deep learning-based model may include a Convolutional Neural Network (CNN), a Recurrent Neural Network (RNN), a long-short-term memory network (LSTM), and the like.

Therefore, more personalized and accurate service distribution is realized, and the service quality, the user satisfaction degree and the service efficiency are improved, and a long-term user relationship is established. Specifically, whether the user is a return customer or not is detected, so that loyalty and historical service conditions of the user can be identified, and more personalized and accurate service is provided for the user; feedback of the user on the service quality can be collected in time by inquiring the satisfaction degree of the user on the historical service personnel, and a basis is provided for improving the service quality and the satisfaction degree of the user; when users satisfy the historical service personnel, the historical service personnel are directly used as target service personnel, so that the service distribution time and resource consumption are reduced, and the service efficiency is improved; when the user is not satisfied with the history service personnel, the first N labels of the semantic information are acquired according to the feedback information of the user, so that the user requirements and the professional ability of the target service personnel are better matched, and the service quality is improved; the method is beneficial to establishing long-term user relationship, and the satisfaction degree and the loyalty degree of users can be improved by paying attention to and adjusting the satisfaction degree of the returning customers, so that the customer population is further expanded.

For example, a user interacts with a virtual assistant of a gym to provide information about their fitness needs and goals, such as: "I want to lose weight and shape. "

The target server detects whether the user is a return guest and determines that the user is a return guest if the user has previously used a personal trainer named trainer A.

The first terminal device plays a first interactive video in which the virtual assistant asks the user if he is satisfied with the previous personal trainer a.

The user replies through voice: "I are not satisfied with coach A because his training method is too aggressive to I. "

Based on the user's feedback information, the target server detects that the user is not satisfied with the history attendant (coach A).

The target server extracts the first N labels of the user's needs (e.g., n=2), for example: [ "weight loss", "shaping" ].

The target server stores information of a plurality of personal coaches, and queries the first N tags of each coach, such as:

coach B tag: [ "weight-reducing", "shaping

Coach C tag: [ "muscle-building", "strength training" ] and

coach D's tag: [ "yoga", "flexibility" ] and

the target server calculates the similarity of the semantic information label of the user to the label of each personal trainer, for example, the similarity corresponding to trainer B, C, D is 100%, 30%, 50% respectively, and the personal trainer corresponding to the highest similarity is trainer B.

And the target server takes the coach B corresponding to the highest similarity as a recommended target service person.

In some embodiments, the method further comprises:

and sending the first electronic record and/or the second electronic record to the first terminal device.

Therefore, the user can directly view the record on the first terminal equipment without logging in other platforms or using other equipment; the method and the device are convenient for the user to quickly acquire the recorded information and improve the user experience.

In some embodiments, the sending the first electronic record and/or the second electronic record to the first terminal device comprises:

using the first terminal equipment display record button;

when a clicking operation for the record button is received, displaying a payment interface by using the first terminal equipment;

and after the user pays successfully, the first electronic record and/or the second electronic record are/is sent to the first terminal equipment.

Thus, providing a pay-download service for electronic recordings helps to provide higher quality recordings to users. By presenting the record download button on the first terminal device, the user may conveniently choose to download the first electronic record and/or the second electronic record. In addition, after the user clicks the download button, the first terminal device displays a payment interface, so that the payment process is simpler, more convenient and quicker. The first electronic record and/or the second electronic record are used as payment content, so that a new income source is created for a service party providing the virtual object interaction function. After paying a certain fee, the user can obtain more detailed and professional answers and suggestions, thereby improving the profitability of the service provider. When the user pays successfully, more detailed and professional answers and suggestions can be obtained, so that the satisfaction degree of the user on the service is improved. This will encourage users to prefer to use and pay for similar services in the future, resulting in good consumption habits. Because of the diversity of user demands, the server needs to continuously update and enrich the content provided by the virtual objects to meet the demands of different users. By setting paid content, the service party can obtain more funds to be put into the content innovation, thereby improving the knowledge level and quality of service of the virtual object.

displaying a first record button and a second record button by using the first terminal equipment;

when a clicking operation for the first record button is received, the first electronic record is sent to the first terminal equipment;

when a clicking operation for the second record button is received, displaying a payment interface by using the first terminal equipment; and after the user pays successfully, the second electronic record is sent to the first terminal equipment.

Thereby, a free download service of the first electronic record is provided, and a pay download service of the second electronic record is provided. Through respectively showing the first record downloading button and the second record downloading button on the first terminal device, the user can select to download the first electronic record and/or the second electronic record according to own requirements, so that a larger selection space is provided for the user, and the user satisfaction is improved. The user can directly click the corresponding download button to obtain the required electronic record, so that the operation flow is simplified. When a user clicks a first record button, a first electronic record can be obtained without payment; when the user clicks the second record button, the first terminal device displays a payment interface, and the second electronic record can be obtained after the payment is completed. The first electronic record is provided as free content and the second electronic record is provided as paid content, which is helpful to promote the perception of the service value by the user. After obtaining the basic information for free, the user may prefer to pay for more detailed, professional answers and advice. By setting a payment interface for the second electronic record, the service party can realize charging service, create a new revenue source for the service party providing the virtual object interaction function, and encourage the service party to continuously improve the service quality and improve the user satisfaction. After experiencing free service, users generate demands for paid service, which helps to stimulate consumer upgrades. Users will prefer to try paid services on the basis of satisfying free services, thereby forming good consumption habits and promoting market development. By setting different acquisition modes for different types of electronic records, resource allocation is facilitated to be optimized. The service side can pay more effort to perform content innovation and improve service quality for paid content, and simultaneously ensure that the basic requirements of free content are met.

In some embodiments, the method further comprises:

Therefore, timely response and processing of the emotion of the user are realized by acquiring the emotion type of the user and taking corresponding measures according to the emotion type, user experience, interactivity, emotion stability and service efficiency are improved, and meanwhile, the service process is optimized. Specifically, by detecting the emotion type of the user and playing the second interactive video, the emotion of the user is pacified by adopting the virtual object, the demand and emotion change of the user can be responded in time, the interactivity with the user is enhanced, and the user is more concerned and concerned; the negative emotion of the user is pacified in time, so that the stability of the emotion of the user is recovered, and the sensitivity of the user to problems in the service process is reduced; by timely responding and processing the emotion of the user, the service process can be optimized, and the pertinence and individuation of the service are improved.

In some embodiments, the identifying the emotion classification of the user according to the received input information includes: and inputting the received input information into an emotion recognition model to obtain the emotion type of the user. The emotion recognition model may be obtained by training a deep learning-based model, for example, and the deep learning-based model may include a Convolutional Neural Network (CNN), a Recurrent Neural Network (RNN), a long-short-term memory network (LSTM), and the like.

Taking an online medical consultation platform as an example, a user sends an access request through a mobile phone (first terminal device) and establishes communication connection with a target server providing an interaction function of a virtual doctor. The user interacts with the virtual doctor to provide symptom information to the virtual doctor, such as by text entry: "I have severe headache", "eat nothing to eat", "don't know why, feel very nausea. The target server extracts semantics from the input information to obtain semantic information of the user, such as headache and nausea. And generating a first electronic record according to the semantic information and a preset record template. The first electronic record includes text descriptions, tables and figures, such as analysis of possible causes of headache and nausea, probability of illness, etc. Based on the received input information, the platform recognizes the user's emotion as "anxiety". And detecting that the anxiety belongs to a preset emotion category set, and playing a second interactive video by using the first terminal equipment by the target server. In this second interactive video, the virtual doctor speaks to the user: "I can understand your worry, but please do not worry too much. We need to further understand your condition in order to give a more accurate diagnosis. Suggesting you seek medical attention in time while maintaining good mind. "

In a specific application scenario, the embodiment of the application further provides a record generation method, which is used for providing a record generation function for the virtual object interaction process, and the method comprises the following steps:

acquiring semantic information of the user according to all input information;

generating a first electronic record according to the semantic information and a preset record template, wherein in the first electronic record, a display mode comprises one or more forms of texts, tables and graphs;

generating a second electronic record according to the semantic information and a preset recording rule, wherein in the second electronic record, the display mode comprises one or more forms of texts, tables, graphs, voices, animations and images; when the input information of the user comprises voice information, in the second electronic record, the display mode comprises voice, and the display content comprises all voice information input by the user; when the input information of the user comprises image information, in the second electronic record, the display mode comprises images, and the display content comprises all the image information input by the user;

Detecting whether the user is a return guest;

when the user is not a return guest, acquiring the first N labels of the semantic information, wherein N is a positive integer; respectively acquiring the first N labels of a plurality of service personnel; respectively calculating the similarity of the label of the semantic information and the label of each service person; taking the service personnel corresponding to the highest similarity as a target service personnel;

when the user is satisfied with the history service personnel, taking the history service personnel as a target service personnel;

when the user is not satisfied with the history service personnel, acquiring the first N labels of the semantic information, wherein N is a positive integer; respectively acquiring the first N labels of a plurality of service personnel; respectively calculating the similarity of the label of the semantic information and the label of each service person; taking the service personnel corresponding to the highest similarity as the target service personnel;

Transmitting the first electronic record and/or the second electronic record to a third terminal device of the target service personnel so that the target service personnel can provide services for the user according to the first electronic record and/or the second electronic record;

The process of obtaining the record template comprises the following steps:

By way of example, when a user accesses an online banking via a smart phone, a communication connection between the smart phone and a target server is established. The target server is responsible for providing the interactive functionality of the virtual assistant.

During the user's interaction with the virtual assistant, the user may enter questions, voice queries, or upload related files (e.g., a bank bill screenshot). For example, the user asks how to apply for a credit card.

Based on the received input information, the target server will extract the semantic information of the user.

The target server generates a first electronic record according to the semantic information and a preset record template, and displays the first electronic record in a text, table or graphic form, for example, a chart of credit card application flow is displayed.

And the target server generates a second electronic record according to the semantic information and a preset recording rule, and displays the second electronic record in the form of text, form, graph, voice, animation or image. For example, when the user's input information comprises a voice query, all of the user's voice information will be included in the second electronic record; when the input information comprises an image, all image information uploaded by the user will be included in the second electronic record.

The target server detects whether the user has used the online consultation service of the bank.

If the user has used, the virtual assistant will ask the user if he is satisfied with the last service's history service personnel (e.g., bank customer manager A).

The user provides feedback information, e.g. satisfaction or dissatisfaction, via the first terminal device.

If the user is satisfied with the bank client manager A, the target server takes the bank client manager A as a target service person. If the user is not satisfied with the bank customer manager A, the target server acquires the first N labels (such as credit card application, interest rate and preferential price) according to the semantic information of the user, calculates the similarity with a plurality of service personnel, and selects the service personnel with the highest similarity as the target service personnel.

The target server sends the first electronic record and/or the second electronic record to a third terminal device (e.g., a computer or tablet device) of the target attendant so that they provide the service to the user.

During the interaction, the target server obtains the emotion category of the user, such as anxiety, according to all the received input information.

Since it is detected that the emotion category of the user belongs to a preset emotion category set (e.g., anxiety, anger, etc.), the second interactive video is played at the first terminal device to pacify the emotion of the user. In the second interactive video, the virtual assistant says: "I understand your worry, let me solve this problem in detail for you to help you eliminate doubts. "such interactions help to improve user satisfaction with the service and enhance the quality of interaction between the user and the virtual assistant.

(electronic device)

The embodiment of the application also provides an electronic device, the specific embodiment of which is consistent with the embodiment described in the method embodiment and the achieved technical effect, and part of the contents are not repeated.

The electronic device is used for providing record generation functions for virtual object interaction processes, the electronic device comprises a memory and at least one processor, the memory stores a computer program, and the at least one processor is configured to realize the following steps when executing the computer program:

In some embodiments, the at least one processor is configured to obtain the record template when executing the computer program by:

In some embodiments, the at least one processor is configured to execute the computer program to further implement the steps of:

In some embodiments, the at least one processor is configured to obtain the target attendant when executing the computer program by:

respectively acquiring the first N labels of a plurality of service personnel;

In some embodiments, the at least one processor is configured to obtain the first N tags of the semantic information when executing the computer program by:

detecting whether the user is a return guest;

Referring to fig. 3, fig. 3 is a block diagram of an electronic device 10 according to an embodiment of the present application.

The electronic device 10 may for example comprise at least one memory 11, at least one processor 12 and a bus 13 connecting the different platform systems.

Memory 11 may include (computer) readable media in the form of volatile memory, such as Random Access Memory (RAM) 111 and/or cache memory 112, and may further include Read Only Memory (ROM) 113.

The memory 11 also stores a computer program executable by the processor 12 to cause the processor 12 to implement the steps of any of the methods described above.

Memory 11 may also include utility 114 having at least one program module 115, such program modules 115 include, but are not limited to: an operating system, one or more application programs, other program modules, and program data, each or some combination of which may include an implementation of a network environment.

Accordingly, the processor 12 may execute the computer programs described above, as well as may execute the utility 114.

The processor 12 may employ one or more application specific integrated circuits (ASICs, application Specific Integrated Circuit), DSPs, programmable logic devices (PLD, programmableLogic devices), complex programmable logic devices (CPLDs, complex Programmable Logic Device), field programmable gate arrays (FPGAs, fields-Programmable Gate Array), or other electronic components.

Bus 13 may be a local bus representing one or more of several types of bus structures including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor, or any of a variety of bus architectures.

The electronic device 10 may also communicate with one or more external devices such as a keyboard, pointing device, bluetooth device, etc., as well as one or more devices capable of interacting with the electronic device 10 and/or with any device (e.g., router, modem, etc.) that enables the electronic device 10 to communicate with one or more other computing devices. Such communication may be via the input-output interface 14. Also, the electronic device 10 may communicate with one or more networks such as a Local Area Network (LAN), a Wide Area Network (WAN) and/or a public network, such as the Internet, through a network adapter 15. The network adapter 15 may communicate with other modules of the electronic device 10 via the bus 13. It should be appreciated that although not shown, other hardware and/or software modules may be used in connection with the electronic device 10 in actual applications, including, but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID systems, tape drives, data backup storage platforms, and the like.

(computer-readable storage Medium)

The embodiment of the application also provides a computer readable storage medium, and the specific embodiment of the computer readable storage medium is consistent with the embodiment recorded in the method embodiment and the achieved technical effect, and part of the contents are not repeated.

The computer readable storage medium stores a computer program which, when executed by at least one processor, performs the steps of any of the methods or performs the functions of any of the electronic devices described above.

The computer readable medium may be a computer readable signal medium or a computer readable storage medium. In embodiments of the present application, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples (a non-exhaustive list) of the computer-readable storage medium would include the following: an electrical connection having one or more wires, a portable disk, a hard disk, random Access Memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

The computer readable storage medium may include a data signal propagated in baseband or as part of a carrier wave, with readable program code embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable storage medium may also be any computer readable medium that can transmit, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable storage medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing. Program code for carrying out operations of the present invention may be written in any combination of one or more programming languages, including an idol-oriented programming language such as Java, C++ or the like and conventional procedural programming languages, such as the C programming language or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device, partly on a remote computing device, or entirely on the remote computing device or server. In the case of remote computing devices, the remote computing device may be connected to the user computing device through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computing device (e.g., connected via the Internet using an Internet service provider).

(computer program product)

The embodiment of the application also provides a computer program product, the specific embodiment of which is consistent with the embodiment described in the method embodiment and the achieved technical effect, and part of the contents are not repeated.

The present application provides a computer program product comprising a computer program which, when executed by at least one processor, performs the steps of any of the methods or performs the functions of any of the electronic devices described above.

Referring to fig. 4, fig. 4 is a schematic structural diagram of a computer program product according to an embodiment of the present application.

The computer program product is configured to implement the steps of any of the methods described above or to implement the functions of any of the electronic devices described above. The computer program product may employ a portable compact disc read only memory (CD-ROM) and comprise program code and may run on a terminal device, such as a personal computer. However, the computer program product of the present application is not limited thereto, and the computer program product may employ any combination of one or more computer readable media.

The present application has been described in terms of its purpose, performance, advancement, and novelty, and the like, and is thus adapted to the functional enhancement and use requirements highlighted by the patent statutes, but the description and drawings are not limited to the preferred embodiments of the present application, and therefore, all equivalents and modifications that are included in the construction, apparatus, features, etc. of the present application shall fall within the scope of the present application.

Claims

1. A record generation method for providing record generation functionality for a virtual object interaction process, the method comprising:

acquiring semantic information of the user according to all input information;

2. The record generation method according to claim 1, wherein the process of acquiring the record template includes:

3. The record generation method according to claim 1, characterized in that the method further comprises:

4. The record generating method according to claim 3, wherein when the input information of the user includes voice information, in the second electronic record, the presentation means includes voice, and the presentation content includes all voice information input by the user;

5. A record generation method according to claim 3, characterized in that the method further comprises:

6. The record generation method according to claim 5, wherein the process of acquiring the target attendant comprises:

respectively acquiring the first N labels of a plurality of service personnel;

7. The record generation method according to claim 6, wherein the obtaining the first N tags of the semantic information includes:

detecting whether the user is a return guest;

8. The record generation method according to claim 1, characterized in that the method further comprises:

9. An electronic device for providing record generation functionality for a virtual object interaction process, the electronic device comprising a memory and at least one processor, the memory storing a computer program, the at least one processor being configured to implement the following steps when executing the computer program:

10. A computer-readable storage medium, characterized in that it stores a computer program which, when executed by at least one processor, implements the steps of the method of any of claims 1-8 or implements the functionality of the electronic device of claim 9.

11. A computer program product, characterized in that it comprises a computer program which, when executed by at least one processor, implements the steps of the method according to any one of claims 1-8 or the functions of the electronic device according to claim 9.